Detekcija i očitanje registarskih pločica vozila

undergraduate thesis

• Title (english): Detection and Reading of Vehicle License Plates
• Author: Mislav Ivančić
• Mentor: Marin Šilić (mentor)
• Committee member: Marin Šilić (predsjednik povjerenstva)
• Committee member: Petar Afrić (član povjerenstva)
• Committee member: Lucija Šikić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2019-07-12, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu opisuju se metode detekcije i očitanja registracijskih pločica vozila sa slika vozila u raznim osvjetljenjima i pod raznim udaljenostima. Za detekciju koristio se prethodno istreniran model neuronske mreže. Detaljno su opisane konvolucijske neuronske mreže i njihova struktura. Korištena biblioteka za treniranje modela je TensorFlow, te su opisane njene glavne komponente i njihov princip rada. Nakon uspješne detekcije, nad detektiranim pločicama izvršava se očitanje znakova s pločice. Opisane su tehnike optičkog očitanja znakova kao što su pretprocesiranje, prepoznavanje i postprocesiranje. Za očitanje znakova registarskih pločica koristila se biblioteka Tesseract.

Abstract (english)

This paper describes the methods for license plate detection and character recognition for vehicle images in various lighting conditions and various distance of vehicle. For detection, a previous pre-trained model was used. Convolutional neural network and its structure is described in detail. Library used for plate detection is TensorFlow, and its main components and their work principle are described. After successful detection, optical character recognition is preformed. Optical character reading techniques are described such as pre-processing, character recognition and post-processing. Tesseract library was used for character recognition.

• Keywords: Detekcija objekata; duboko učenje; TensorFlow; Tesseract; OCR
• Keywords (english): Object detection; deep learning; TensorFlow; Tesseract; OCR
• Language: croatian
• URN:NBN: urn:nbn:hr:168:742638
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2020-01-07 18:31:32